王 d407ccb773 perf(streaming): optimize TTFT and reduce buffering latency ...

Core changes:
- stream.go: New accumulation buffer architecture with scanner goroutine
  + select loop, MinChars=16, MaxWait=10ms, first-flush-immediate
- dedupe.go: Add TrimContinuationOverlapFromBuilder to avoid string copies
- claude/stream_runtime_core.go: Integrate toolstream for incremental text
- claude/stream_runtime_finalize.go: toolstream flush support
- stream_emitter.js: Reduce DeltaCoalescer thresholds (160->16 chars, 80->20ms)
- empty_retry: Add thinking-aware empty output detection
- Fix reasoning_content leak and finish_reason=null in edge cases
- Fix tail content truncation when max_tokens exceeded

Tests: sync test expectations with upstream for thinking content

2026-05-02 20:28:30 +08:00

..

chat

perf(streaming): optimize TTFT and reduce buffering latency

2026-05-02 20:28:30 +08:00

embeddings

refactor backend API structure

2026-04-26 06:58:20 +08:00

files

feat(openai): retrieve uploaded file metadata

2026-05-02 14:33:42 +07:00

history

feat: add model type support for file uploads with automatic resolution and header propagation

2026-05-02 00:55:17 +08:00

responses

perf(streaming): optimize TTFT and reduce buffering latency

2026-05-02 20:28:30 +08:00

shared

perf(streaming): optimize TTFT and reduce buffering latency

2026-05-02 20:28:30 +08:00

citation_links_test.go

fix(openai): keep citation indexes one-based

2026-04-29 15:43:09 +07:00

deps_injection_test.go

lint

2026-04-27 13:48:55 +08:00

embeddings_route_test.go

refactor backend API structure

2026-04-26 06:58:20 +08:00

error_shape_test.go

refactor backend API structure

2026-04-26 06:58:20 +08:00

file_inline_upload_test.go

feat: add model type support for file uploads with automatic resolution and header propagation

2026-05-02 00:55:17 +08:00

files_route_test.go

feat(openai): retrieve uploaded file metadata

2026-05-02 14:33:42 +07:00

history_split_test.go

feat: add model type support for file uploads with automatic resolution and header propagation

2026-05-02 00:55:17 +08:00

leaked_output_sanitize_test.go

Fix stream compatibility and vision model exposure

2026-04-29 20:23:13 +08:00

models_route_test.go

chore: update project files

2026-04-27 02:09:11 +08:00

stream_status_test.go

perf(streaming): optimize TTFT and reduce buffering latency

2026-05-02 20:28:30 +08:00

test_bridge_test.go

feat(openai): retrieve uploaded file metadata

2026-05-02 14:33:42 +07:00

trace_test.go

refactor backend API structure

2026-04-26 06:58:20 +08:00